CN106355152A - Method and system for identifying current road vehicles as well as car video recorder - Google Patents
Method and system for identifying current road vehicles as well as car video recorder Download PDFInfo
- Publication number
- CN106355152A CN106355152A CN201610779340.8A CN201610779340A CN106355152A CN 106355152 A CN106355152 A CN 106355152A CN 201610779340 A CN201610779340 A CN 201610779340A CN 106355152 A CN106355152 A CN 106355152A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- road
- line
- straight line
- driver
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
- G07C5/085—Registering performance data using electronic data carriers
- G07C5/0866—Registering performance data using electronic data carriers the electronic data carrier being a digital video recorder in combination with video camera
Abstract
The invention provides a method and a system for identifying current road vehicles as well as a car video recorder. The method for identifying the current road vehicles comprises the following steps: a picture of a road on which a driver travels is acquired, two points on a left road edge line and two points on a right road edge line are identified, and intersection points of left and right road edge lines are acquired through computation, that is, a closed area of the road is obtained; four fixed points of at least one vehicle are acquired, and a square frame model just covering each vehicle is established for the vehicle; whether the square frame model of each vehicle intersects the closed area of the road is judged, and if intersection exists, the vehicle travels on the same lane with the vehicle of the driver. With adoption of the method, the detection precision of the car video recorder can be improved greatly, the accuracy for identifying vehicles on the same lane is improved, and safe vehicle driving is guaranteed.
Description
Technical field
The present invention relates to safe driving of vehicle field and in particular to a kind of method of identification present road vehicle, system and
Drive recorder.
Background technology
Drive recorder refers to that registration of vehicle travels the instrument of the relevent informations such as image and sound in way.Driving note is installed
After record instrument, it is able to record that video image and the sound of running car overall process, evidence can be provided for vehicle accident.During driving, side is walked
Record a video in side, time, speed, position are all recorded in video recording simultaneously, and suitable black box can also assist simultaneously and refer to
Lead human pilot and carry out safe driving, reduce the transmission of security incident.
Current drive recorder detection precision is low, and wherein road edge line detection is inaccurate, and vehicle often occurs
Keep to the side line too nearly and substantial amounts of false alarm prompting；Additionally, due to road edge line detection inaccurate it is impossible to accurately judge other cars
Whether travel on same track with driver vehicle, whether whether same track vehicle maintained with driver vehicle
Safe distance is it is impossible to make accurate judgement, thus excessive false alarm is it is impossible to auxiliary truly and instruct driver
Member carries out safe driving.
Content of the invention
The present invention in order to solve prior art presence above-mentioned technical problem, there is provided a kind of can Detection accuracy high
The method of identification present road vehicle, system and drive recorder.
For achieving the above object, the invention provides a kind of identification present road vehicle method, comprising:
Obtain driver travel picture, identify left-side course roadside along the line on 2 points and right-side course roadside along the line on
, by calculating the intersection point obtaining left and right two road edge line, that is, obtain the closing surface area of road at 2 points；
Obtain four fixed points of at least one vehicle, and set up one respectively for each vehicle and just frame the square of this vehicle
Frame model；
Judge whether the square box model of vehicle has common factor on the closing surface area of road, when there being common factor, judge this vehicle
With the vehicle of driver in same lanes.
As the preferred technical solution of the present invention, obtain the travel picture of driver in the following manner:
Obtain travel picture using photographic head, picture is carried out gray proces, and pass through Gaussian filter smoothed image.
As the preferred technical solution of the present invention, when after Gaussian filter smoothed image, using having of single order local derviation
Limit difference, to calculate amplitude and the direction of gradient, carries out non-maxima suppression to gradient magnitude, with the detection of dual threashold value-based algorithm with even
Connect road edge, to obtain the image after rim detection, and all straight of described image is obtained using hough line detection algorithm
Line model, travels through all straightways getting, and obtains the angle of all straight lines, judges that this line segment is according to the angle of straight line
The left side on road is along the line or the right is along the line, rejects the line segment not meeting angle and being unsatisfactory for demand, and by the left and right getting side
It is saved in respectively in two set along straight line.
As the preferred technical solution of the present invention, exclusion is carried out to the straight line set of left and right edge and selects, obtain the optimum left side
Road and optimum the right Road.
As the preferred technical solution of the present invention, intersection point judgement is carried out to the left and right edge straight line getting, if intersection point
Too low or excessively off-center axle then selects optimum line segment again, more again does intersection point judgement；Straight to the left and right edge getting
Line intersection point angle angle is judged, if angle is excessive or too small between two road, reacquires optimum line segment, goes forward side by side
Row intersection point judges and angle judges.
As the preferred technical solution of the present invention, obtain in the left and right edge straight line finally getting and last round of circulation
To left and right edge straight line carry out threshold deviation judgement, if with the last round of left and right edge straight line detecting deviate excessive,
It is judged as not getting left and right edge straight line, accent detects, if the deviation from meeting the requirements, then detection road success；If on
The left and right edge straight line that one wheel detects does not have, then again detect.
As the preferred technical solution of the present invention, when judgement has several vehicles with the vehicle of driver in same track
During traveling, choose one or two and be shown on screen from the nearest vehicle of driver vehicle.
As the preferred technical solution of the present invention, when the scan round more than 20 times is not detected by left and right edge straight line, then
It is judged as not having road, and the circuit detecting of erasing.
Present invention also offers a kind of system of identification present road vehicle, comprising:
Road model acquisition module, for obtaining the travel picture of driver, identify left-side course roadside along the line on two
On point is along the line with right-side course roadside 2 points, by calculating the intersection point obtaining left and right two road edge line, that is, obtain road
Closing surface area；
Auto model acquisition module, for obtaining four fixed points of at least one vehicle, and sets up one respectively for each vehicle
The individual square box model just framing this vehicle；And
Processing module, whether the square box model for judging vehicle has common factor on the closing surface area of road, when there being friendship
Collection, judges this vehicle and the vehicle of driver in same lanes.
Present invention also offers a kind of drive recorder, including the identification present road vehicle described in any of the above-described it is
System.
The identification method of present road vehicle of the present invention, system and drive recorder can reach following beneficial effect:
The method of the identification present road vehicle of the present invention, by including: obtain the travel picture of driver, identify a left side
2 points on side line roadside is along the line and right-side course roadside along the line on 2 points, obtain left and right two road edge lines by calculating
Intersection point, that is, obtain the closing surface area of road；Obtain four fixed points of at least one vehicle, and build respectively for each vehicle
A vertical square box model just framing this vehicle；The square box model judging vehicle is on the closing surface area of road
No have common factor, when there being common factor, judges that this vehicle and the vehicle of driver, in same lanes, are greatly improved drive recorder
Detection precision, improve the degree of accuracy identifying same track vehicle, can although be prevented effectively from driver vehicle distance too
Closely, but the frequent false alarm not caused in same track.
The system of the identification present road vehicle of the present invention, by including: road model acquisition module, drive for obtaining
Member travel picture, identify left-side course roadside along the line on 2 points and right-side course roadside along the line on 2 points, by meter
Calculate the intersection point obtaining left and right two road edge line, that is, obtain the closing surface area of road；Auto model acquisition module, is used for
Obtain four fixed points of at least one vehicle, and set up a square box mould just framing this vehicle respectively for each vehicle
Type；And processing module, whether the square box model for judging vehicle have common factor on the closing surface area of road, when having
Occur simultaneously, judge that this vehicle and the vehicle of driver, in same lanes, are greatly improved the detection precision of drive recorder,
Improve the degree of accuracy identifying same track vehicle, can although being prevented effectively from too near with driver vehicle's distance, but not same
One track and the frequent false alarm that causes.
The drive recorder of the present invention, by including the system of above-mentioned identification present road vehicle, is greatly improved driving
The detection precision of monitor, improves the degree of accuracy identifying same track vehicle, can although being prevented effectively from and driver vehicle
Distance is too near, but the frequent false alarm not caused in same track, it is to avoid the operation to human pilot mislead it is ensured that
The safe driving of vehicle.
Brief description
The present invention is further detailed explanation with reference to the accompanying drawings and detailed description.
The method flow diagram of the embodiment that the method that Fig. 1 identifies present road vehicle for the present invention provides；
The structured flowchart of the embodiment that the system that Fig. 2 identifies present road vehicle for the present invention provides.
The object of the invention is realized, functional characteristics and advantage will be described further in conjunction with the embodiments referring to the drawings.
Specific embodiment
It should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
As Fig. 1, a kind of method of identification present road vehicle, comprising:
Step 11, obtain driver travel picture, identify left-side course roadside along the line on 2 points and right-side course roadside
On along the line 2 points, by calculating the intersection point obtaining left and right two road edge line, that is, obtain the closing surface area of road；
Step 12, obtain four of at least one vehicle fixed points, and set up one respectively for each vehicle and just frame this car
Square box model；In this step, obtain various vehicle photos in a large number by many experiments, using cascade
Classifier training method obtains the xml document of training sample, by opencv pattern recognition and calculate various cars
Model, and to obtain four fixed points of at least one vehicle；
Step 13, judge whether the square box model of vehicle has common factor on the closing surface area of road, when there being common factor, execution
Step 14, otherwise return to step 11 continue executing with；
Step 14, judge the vehicle of this vehicle and driver in same lanes.
In being embodied as, the travel picture of obtaining step 11 driver in the following manner:
Obtain travel picture using photographic head, picture is carried out gray proces, and pass through Gaussian filter smoothed image.
In being embodied as, when, after Gaussian filter smoothed image, the finite difference using single order local derviation calculates ladder
The amplitude of degree and direction, carry out non-maxima suppression to gradient magnitude, with the detection of dual threashold value-based algorithm and linking-up road edge, to obtain
Image to after rim detection, and all straight line models of described image are obtained using hough line detection algorithm, traversal is all
The straightway getting, obtains the angle of all straight lines, according to the angle of straight line judge this line segment be the left side of road along the line also
It is that the right is along the line, reject the line segment not meeting angle and being unsatisfactory for demand, and edge straight line in the left and right getting is preserved respectively
To in two set.
In being embodied as, exclusion is carried out to the straight line set of left and right edge and selects, obtain optimum left side Road and optimum is right
By-pass route.
In being embodied as, intersection point judgement is carried out to the left and right edge straight line getting, if intersection point is too low or excessively deviates
Central shaft then selects optimum line segment again, more again does intersection point judgement；To the left and right edge straight-line intersection angle angle getting
Judged, if angle is excessive or too small between two road, reacquires optimum line segment, and carry out intersection point judgement and folder
Angle judges.
In being embodied as, straight to the left and right edge getting in the left and right edge straight line finally getting and last round of circulation
Line carries out threshold deviation judgement, if excessive with the last round of left and right edge straight line deviation detecting, is judged as not obtaining
To left and right edge straight line, accent detects, if the deviation from meeting the requirements, then detection road success；If the last round of left side detecting
The right does not have along straight line, then again detect.
Preferably, when judging to there is the vehicle of several vehicles and driver in same lanes, choose one or two
It is shown on screen from the nearest vehicle of driver vehicle, so not only can give driver's preferably visual experience, and
Because display vehicle is less, thus the vehicle avoiding above same track may seem mixed and disorderly too much, it is unfavorable for driver
Viewing.
In being embodied as, when the scan round more than 20 times is not detected by left and right edge straight line, then it is judged as not having road,
And the circuit detecting of erasing.
As shown in Fig. 2 the system of identification present road vehicle, comprising:
Road model acquisition module 21, for obtaining the travel picture of driver, identify that left-side course roadside is along the line on
2 points and right-side course roadside along the line on 2 points, by calculating the intersection point obtaining left and right two road edge lines, that is, obtain road
Closing surface area；
Auto model acquisition module 22, for obtaining four fixed points of at least one vehicle, and sets up respectively for each vehicle
One square box model just framing this vehicle；And
Processing module 23, whether the square box model for judging vehicle has common factor on the closing surface area of road, when having
Occur simultaneously, judge this vehicle and the vehicle of driver in same lanes.
Present invention also offers a kind of drive recorder, including the identification present road vehicle described in any of the above-described it is
System.
Although the foregoing describing the specific embodiment of the present invention, those skilled in the art should be appreciated that this
It is merely illustrative of, various changes or modifications can be made to present embodiment, the principle without departing from the present invention and essence,
Protection scope of the present invention is only limited by the claims that follow.
Claims (10)
1. a kind of method of identification present road vehicle is it is characterised in that include:
Obtain driver travel picture, identify left-side course roadside along the line on 2 points and right-side course roadside along the line on
, by calculating the intersection point obtaining left and right two road edge line, that is, obtain the closing surface area of road at 2 points；
Obtain four fixed points of at least one vehicle, and set up one respectively for each vehicle and just frame the square of this vehicle
Frame model；
Judge whether the square box model of vehicle has common factor on the closing surface area of road, when there being common factor, judge this vehicle
With the vehicle of driver in same lanes.
2. drive it is characterised in that obtaining in the following manner according to the method for the identification present road vehicle described in claim 1
The travel picture of the person of sailing:
Obtain travel picture using photographic head, picture is carried out gray proces, and pass through Gaussian filter smoothed image.
3. put down by Gaussian filter it is characterised in that working as according to the method for the identification present road vehicle described in claim 2
After sliding image, calculate amplitude and the direction of gradient using the finite difference of single order local derviation, non-maximum is carried out to gradient magnitude
Suppression, with the detection of dual threashold value-based algorithm and linking-up road edge, to obtain the image after rim detection, and using the inspection of hough straight line
Method of determining and calculating obtains all straight line models of described image, travels through all straightways getting, and obtains the angle of all straight lines, root
According to the angle of straight line judge this line segment be road the left side is along the line or the right along the line, reject and do not meet angle and be unsatisfactory for demand
Line segment, and edge straight line in the left and right getting is saved in two set respectively.
4. according to the identification present road vehicle described in claim 3 method it is characterised in that to the straight line set of left and right edge
Carry out exclusion to select, obtain optimum left side Road and optimum the right Road.
5. according to the identification present road vehicle described in claim 4 method it is characterised in that to the left and right edge getting
Straight line carries out intersection point judgement, if intersection point is too low or excessively off-center axle, again selects optimum line segment, more again does intersection point
Judge；The left and right edge straight-line intersection angle angle getting is judged, if between two road, angle is excessive or mistake
Little then reacquisition optimum line segment, and carry out intersection point judgement and angle judgement.
6. according to the identification present road vehicle described in claim 5 method it is characterised in that to the left and right finally getting
The left and right edge straight line getting in edge straight line and last round of circulation carries out threshold deviation judgement, if detected with last round of
Left and right edge straight line deviate excessive, then be judged as not getting left and right edge straight line, accent detects, if the deviation from conforming to
Ask, then the success of detection road；If the last round of left and right edge straight line detecting does not have, again detect.
7. according to the identification present road vehicle described in any one of claim 1 to 6 method it is characterised in that when judgement is deposited
When the vehicle of several vehicles and driver is in same lanes, choose one or two from the nearest vehicle of driver vehicle
It is shown on screen.
8. according to the method identifying present road vehicle described in claim 7 it is characterised in that working as the scan round more than 20 times
It is not detected by left and right edge straight line, then be judged as not having road, and the circuit detecting of erasing.
9. a kind of system of identification present road vehicle is it is characterised in that include:
Road model acquisition module, for obtaining the travel picture of driver, identify left-side course roadside along the line on two
On point is along the line with right-side course roadside 2 points, by calculating the intersection point obtaining left and right two road edge line, that is, obtain road
Closing surface area；
Auto model acquisition module, for obtaining four fixed points of at least one vehicle, and sets up one respectively for each vehicle
The individual square box model just framing this vehicle；And
Processing module, whether the square box model for judging vehicle has common factor on the closing surface area of road, when there being friendship
Collection, judges this vehicle and the vehicle of driver in same lanes.
10. a kind of drive recorder is it is characterised in that include the system of the identification present road vehicle described in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610779340.8A CN106355152A (en) | 2016-08-30 | 2016-08-30 | Method and system for identifying current road vehicles as well as car video recorder |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610779340.8A CN106355152A (en) | 2016-08-30 | 2016-08-30 | Method and system for identifying current road vehicles as well as car video recorder |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106355152A true CN106355152A (en) | 2017-01-25 |
Family
ID=57856654
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610779340.8A Pending CN106355152A (en) | 2016-08-30 | 2016-08-30 | Method and system for identifying current road vehicles as well as car video recorder |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106355152A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392093A (en) * | 2017-06-14 | 2017-11-24 | 北京遥感设备研究所 | A kind of rail identifying system being combined based on machine learning and gray projection algorithm |
| CN110728680A (en) * | 2019-10-25 | 2020-01-24 | 上海眼控科技股份有限公司 | Automobile data recorder detection method and device, computer equipment and storage medium |
| CN114127655A (en) * | 2019-05-20 | 2022-03-01 | 祖克斯有限公司 | Enclosed lane detection |
-
2016
- 2016-08-30 CN CN201610779340.8A patent/CN106355152A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392093A (en) * | 2017-06-14 | 2017-11-24 | 北京遥感设备研究所 | A kind of rail identifying system being combined based on machine learning and gray projection algorithm |
| CN107392093B (en) * | 2017-06-14 | 2019-01-01 | 北京遥感设备研究所 | A kind of rail identifying system combined based on machine learning and gray projection algorithm |
| CN114127655A (en) * | 2019-05-20 | 2022-03-01 | 祖克斯有限公司 | Enclosed lane detection |
| CN114127655B (en) * | 2019-05-20 | 2023-12-22 | 祖克斯有限公司 | Closed lane detection |
| CN110728680A (en) * | 2019-10-25 | 2020-01-24 | 上海眼控科技股份有限公司 | Automobile data recorder detection method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6416293B2 (en) | Method of tracking a target vehicle approaching a car by a car camera system, a camera system, and a car | |
| CN104008645B (en) | One is applicable to the prediction of urban road lane line and method for early warning | |
| US10147002B2 (en) | Method and apparatus for determining a road condition | |
| US20200406897A1 (en) | Method and Device for Recognizing and Evaluating Roadway Conditions and Weather-Related Environmental Influences | |
| JP5966965B2 (en) | Lane boundary departure control device and lane boundary departure suppression method | |
| CN101030256B (en) | Method and apparatus for cutting vehicle image | |
| CN108281041A (en) | A kind of parking space's detection method blended based on ultrasonic wave and visual sensor | |
| CN105539293B (en) | Lane departure warning method and device and car steering accessory system | |
| CN106778593A (en) | A kind of track level localization method based on the fusion of many surface marks | |
| CN105620489A (en) | Driving assistance system and real-time warning and prompting method for vehicle | |
| CN104574376A (en) | Anti-collision method based on joint verification of binocular vision and laser radar in congested traffic | |
| US9257045B2 (en) | Method for detecting a traffic lane by means of a camera | |
| CN104129389A (en) | Method for effectively judging and recognizing vehicle travelling conditions and device thereof | |
| CN104573646A (en) | Detection method and system, based on laser radar and binocular camera, for pedestrian in front of vehicle | |
| WO2013136878A1 (en) | Object detection device | |
| CN107804226A (en) | Trailer lane departur warning and wave alarm | |
| CN101135558A (en) | Vehicle anti-collision early warning method and apparatus based on machine vision | |
| CN101131321A (en) | Real-time safe interval measurement method and device used for vehicle anti-collision warning | |
| KR20090130977A (en) | System of traffic conflict decision for signalized intersections using image processing technique | |
| CN108764108A (en) | A kind of Foregut fermenters method based on Bayesian inference | |
| CN105654073A (en) | Automatic speed control method based on visual detection | |
| KR101584907B1 (en) | Method and Apparatus for recognizing lane using region of interest | |
| CN111915883A (en) | Road traffic condition detection method based on vehicle-mounted camera shooting | |
| CN106355152A (en) | Method and system for identifying current road vehicles as well as car video recorder | |
| CN110991264A (en) | Front vehicle detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170125 |